Data Science has gained a lot of popularity in the last few years. This field's primary focus is to convert meaningful data into marketing and business strategies which helps a company grow. The data is stored and researched to get in a logical solution. Previously only the top IT companies were involved in this field but today businesses from various sector and fields such as e-commerce, health care, finance, and others are using data analytics. There are various tools available for data analytics such as Hadoop, R programming, SAS, SQL and many more. However the most popular and easy to use tools for data analytics is Python.

Last week, Hugging Face, a startup specializing in natural language processing, released a landmark update to their popular Transformers library, offering unprecedented compatibility between two major deep learning frameworks, PyTorch and TensorFlow 2.0. Transformers (formerly known as pytorch-transformers and pytorch-pretrained-bert) provides general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet…) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with over 32 pretrained models in 100 languages and deep interoperability between TensorFlow 2.0 and PyTorch.

Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks or Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles of deep learning from both an algorithmic and computational perspectives.

Machine learning is experiencing an explosion of software and hardware solutions, and needs industry-standard performance benchmarks to drive design and enable competitive evaluation. However, machine learning training presents a number of unique challenges to benchmarking that do not exist in other domains: (1) some optimizations that improve training throughput actually increase time to solution, (2) training is stochastic and time to solution has high variance, and (3) the software and hardware systems are so diverse that they cannot be fairly benchmarked with the same binary, code, or even hyperparameters. We present MLPerf, a machine learning benchmark that overcomes these challenges. We quantitatively evaluate the efficacy of MLPerf in driving community progress on performance and scalability across two rounds of results from multiple vendors.

In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the data rate. We propose a band switching approach based on machine learning that does not require any measurement gap. Our proposed classifier-based band switching policy instead exploits spatial and spectral correlation between radio frequency signals in different bands based on knowledge of the UE location. We focus on switching between a lower (e.g. 3.5 GHz) band and a millimeter wave band (e.g. 28 GHz), and design and evaluate two classification models that are trained on a ray-tracing dataset. A key insight is that measurement gaps are overkill, in that only the relative order of the bands is necessary for band selection, rather than a full channel estimate. Our proposed machine learning-based policies achieve roughly 30% improvement in mean effective rates over those of the industry standard policy, while achieving misclassification errors well below 0.5%.

Designing deep learning models for highly-constrained hardware would allow imbuing many edge devices with intelligence. Microcontrollers (MCUs) are an attractive platform for building smart devices due to their low cost, wide availability, and modest power usage. However, they lack the computational resources to run neural networks as straightforwardly as mobile or server platforms, which necessitates changes to the network architecture and the inference software. In this work, we discuss the deployment and memory concerns of neural networks on MCUs and present a way of saving memory by changing the execution order of the network's operators, which is orthogonal to other compression methods. We publish a tool for reordering operators of TensorFlow Lite models and demonstrate its utility by sufficiently reducing the memory footprint of a CNN to deploy it on an MCU with 512KB SRAM.

Road scenes analysis in adverse weather conditions by polarization-encoded images and adapted deep learning Rachel Blin 1, Samia Ainouz 1, St ephane Canu 1 and Fabrice Meriaudeau 2 Abstract -- Object detection in road scenes is necessary to develop both autonomous vehicles and driving assistance systems. Even if deep neural networks for recognition task have shown great performances using conventional images, they fail to detect objects in road scenes in complex acquisition situations. In contrast, polarization images, characterizing the light wave, can robustly describe important physical properties of the object even under poor illumination or strong reflections. This paper shows how non-conventional polarimetric imaging modality overcomes the classical methods for object detection especially in adverse weather conditions. The efficiency of the proposed method is mostly due to the high power of the polarimetry to discriminate any object by its reflective properties and on the use of deep neural networks for object detection. Our goal by this work, is to prove that polarimetry brings a real added value compared with RGB images for object detection. Experimental results on our own dataset composed of road scene images taken during adverse weather conditions show that polarimetry together with deep learning can improve the state-of-the-art by about 20% to 50% on different detection tasks.

We experimentally achieve a 19% capacity gain per Watt of electrical supply power in a 12-span link by eliminating gain flattening filters and optimizing launch powers using machine learning by deep neural networks in a massively parallel fiber context.

--Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However, deep learning-based perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images. Nevertheless, the vast majority of such demonstrations focus on perception that is disembodied from end-to-end control. These attacks target deep neural network models for end-to-end autonomous driving control. A systematic investigation shows that such attacks are easy to engineer, and we describe scenarios (e.g., right turns) in which they are highly effective. We define several objective functions that quantify the success of an attack and develop techniques based on Bayesian Optimization to efficiently traverse the search space of higher dimensional attacks. Additionally, we define a novel class of hijacking attacks, where painted lines on the road cause the driverless car to follow a target path. Through the use of network deconvolution, we provide insights into the successful attacks, which appear to work by mimicking activations of entirely different scenarios. With billions of dollars being pumped into autonomous vehicle research to reach Level 5 Autonomy, where vehicles will not require human intervention, safety has become a critical issue [3]. Remarkable advances in deep learning, in turn, suggest such approaches as natural candidates for integration into autonomous control. One way to use deep learning in autonomous driving control is in an end-to-end (e2e) fashion, where learned models directly translate perceptual inputs into control decisions, such as the vehicle's steering angle. Indeed, recent work demonstrated such approaches to be remarkably successful, particularly when learned to imitate human drivers [4]. Despite the success of deep learning in enabling greater autonomy, a number of parallel efforts also have exhibited concerning fragility of deep learning approaches to small adversarial perturbations of inputs such as images [5], [6].

Wide adoption of complex RNN based models is hindered by their inference performance, cost and memory requirements. To address this issue, we develop AntMan, combining structured sparsity with low-rank decomposition synergistically, to reduce model computation, size and execution time of RNNs while attaining desired accuracy. AntMan extends knowledge distillation based training to learn the compressed models efficiently. Our evaluation shows that AntMan offers up to 100x computation reduction with less than 1pt accuracy drop for language and machine reading comprehension models. Our evaluation also shows that for a given accuracy target, AntMan produces 5x smaller models than the state-of-art. Lastly, we show that AntMan offers super-linear speed gains compared to theoretical speedup, demonstrating its practical value on commodity hardware.